© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83600
    Prev
    Next
    INDEX
    Explanations

    may also

    np_acts-logits-general · gemini-2.5-flash-lite

    DRY, Examples, Problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     плат
    0.52
     高校
    0.49
     тури
    0.48
    omnia
    0.47
    𝘳
    0.46
     The
    0.45
    IZE
    0.44
    િયો
    0.44
     радио
    0.44
     кампа
    0.43
    POSITIVE LOGITS
     fundament
    0.44
    取出
    0.42
     HashMap
    0.41
     Preset
    0.41
     glo
    0.40
    ชื่อ
    0.40
    ளாக்
    0.39
    쇄
    0.39
     alumin
    0.39
    花生
    0.39
    Activations Density 0.000%

    No Known Activations